AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Neural Sampling in Hierarchical Exponential-family Energy-based Models

Xingsi Dong, Si Wu

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use nonlinear statistic sigmoid(x) instead of linear x in HEE (ablation)HEE (HEE-NL vs HEE-L) · 2D synthetic datasets and FashionMNISTgeneration quality (qualitative)Improved
marginal generation instead of joint generation (ablation)HEE-NL-A · CIFAR10 unconditionalimage quality (Inception score, FID)Improved
marginal generation instead of joint generation (ablation)HEE-NL · 2D synthetic datasets and FashionMNISTconvergence speed (qualitative)Improved
add neural adaptation as momentum (SLD sampling instead of LS)HEE-NL · inference sampling speedsampling speedImproved
increase adaptation strength mHEE-NL-A · CIFAR10 inferenceoscillation frequency and onset transients: 20-80 HzImproved
deeper layers of the networkHEE-NL-A · CIFAR10 linear SVM on latent responsesclassification accuracyImproved
joint generation with HEE-NLHEE-NL · 2D synthetic datasetsmode coverageHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy